Oindrila Saha
11 papers · 2019–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (24) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint 𧬠Topic Evolution
ποΈ
Keyword Collector
(51)
β
The Questioner
π
Conference Pioneer
π
Century Club Β· Bronze
Top co-authors
Research topics
Computer Vision
(7)
Deep Learning
(6)
Artificial Intelligence
(5)
Machine Learning
(5)
Analysis
(5)
Core AI
(5)
Models
(4)
Generation
(3)
Learning Types Β· Machine Learning
(3)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Paradigms
(1)
Learning Types Β· Deep Learning
(1)
Optimization & Theory
(1)
Keywords
vision-language model
(3)
zero-shot classification
(2)
multimodal large language model
(2)
large language model
(2)
transductive learning
(1)
model calibration
(1)
semantic segmentation
(1)
image synthesis
(1)
image generation
(1)
text-to-image generation
(1)
fine-grained classification
(1)
classification abstention
(1)
visual recognition
(1)
fine-grained recognition
(1)
recurrent neural network
(1)
weakly supervised learning
(1)
convolutional neural network
(1)
memory efficiency
(1)
inductive bia
(1)
diffusion model
(1)
Papers
3D Space as a Scratchpad for Editable Text-to-Image Generation
CVPR 2026
Not All Birds Look The Same: Identity-Preserving Generation For Birds
CVPR 2026
RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs
CVPR 2026
You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction
WACV 2026
Generate, Transduct, Adapt: Iterative Transduction with VLMs
ICCV 2025
Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions
CVPR 2024
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
NeurIPS 2024
GanOrCon: Are Generative Models Useful for Few-Shot Segmentation?
CVPR 2022
Improving Few-Shot Part Segmentation Using Coarse Supervision
ECCV 2022
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
NeurIPS 2020
Learning with Multitask Adversaries using Weakly Labelled Data for Semantic Segmentation in Retinal Images
MIDL 2019